Concept-oriented video skimming and adaptation via semantic classification
Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval
Video abstraction: A systematic review and classification
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Split-screen dynamically accelerated video summaries
Proceedings of the international workshop on TRECVID video summarization
TVS '08 Proceedings of the 2nd ACM TRECVid Video Summarization Workshop
Fast analysis of scalable video for adaptive browsing interfaces
Computer Vision and Image Understanding
Dynamic video summarization using two-level redundancy detection
Multimedia Tools and Applications
An integrated approach to summarization and adaptation using H.264/MPEG-4 SVC
Image Communication
Content-based image and video indexing and retrieval
Proceedings of the 2005 joint Chinese-German conference on Cognitive systems
Sequence-kernel based sparse representation for amateur video summarization
J-MRE '11 Proceedings of the 2011 joint ACM workshop on Modeling and representing events
Video summarization: techniques and classification
ICCVG'12 Proceedings of the 2012 international conference on Computer Vision and Graphics
Dynamic video summarization with content analysis
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Infinite Dirichlet mixture models learning via expectation propagation
Advances in Data Analysis and Classification
Surveillance video synopsis in the compressed domain for fast video browsing
Journal of Visual Communication and Image Representation
Key observation selection-based effective video synopsis for camera network
Machine Vision and Applications
Hi-index | 0.00 |
We propose a unified approach for summarization based on theanalysis of video structures and video highlights. Our approachemphasizes both the content balance and perceptual quality of asummary. Normalized cut algorithm is employed to globally andoptimally partition a video into clusters. A motion attention modelbased on human perception is employed to compute the perceptualquality of shots and clusters. The clusters, together with thecomputed attention values, form a temporal graph similar to Markovchain that inherently describes the evolution and perceptualimportance of video clusters. In our application, the flow of atemporal graph is utilized to group similar clusters into scenes,while the attention values are used as guidelines to selectappropriate sub-shots in scenes for summarization.